System

Abstract

An object of a system according to an embodiment is to provide a foreign language learning environment corresponding to flexible time and level.SOLUTION: A system includes a voice text conversion part, a generation AI part, a text-to-speech part, a foreign language selection part, and a conversation field designation part. The speech-text conversion unit converts speech into text. The generated AI unit generates a response based on the text converted by the speech-to-text conversion unit. The text-to-speech unit converts the text generated by the generation and AI unit into voice. The foreign language selection unit selects a foreign language to be learned. The conversation field designation unit designates a field and a level in which a conversation is desired.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies have had the problem of making it difficult to provide a learning environment that is flexible in terms of time and level when learning a foreign language.

[0005] The system according to the embodiment aims to provide a foreign language learning environment that is flexible in terms of time and level. [Means for solving the problem]

[0006] The system according to the embodiment includes a speech-to-text conversion unit, a generation AI unit, a text-to-speech conversion unit, a foreign language selection unit, and a conversation field designation unit. The speech-to-text conversion unit converts speech into text. The generation AI unit generates a response based on the text converted by the speech-to-text conversion unit. The text-to-speech conversion unit converts the text generated by the generation AI unit into speech. The foreign language selection unit selects the foreign language you want to learn. The conversation field designation unit designates the field and level you want to talk in. [Effects of the Invention]

[0007] The system according to the embodiment can provide a foreign language learning environment that is flexible in terms of time and level. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The online foreign language conversation classroom system according to an embodiment of the present invention is a system that allows users to freely learn a foreign language by combining a speech-to-text conversion function with a chat-based generation AI. This allows users to efficiently learn a foreign language even in a short amount of time. For example, a user can practice business English conversation in 20 minutes of their free time. Furthermore, users can learn at their own pace without feeling embarrassed because they have no prior knowledge. Furthermore, since the system is available to users around the world, learning can be done from a global perspective.

[0029] The online foreign language conversation classroom system according to the embodiment includes a speech-to-text conversion unit, a generation AI unit, a text-to-speech conversion unit, a foreign language selection unit, and a conversation field designation unit. The speech-to-text conversion unit converts the speech spoken by a user into text. For example, the speech-to-text conversion unit converts speech to text using a speech recognition algorithm. The speech-to-text conversion unit can also convert speech to text by specifying software to be used. The generation AI unit generates a response based on the text converted by the speech-to-text conversion unit. For example, the speech-to-text conversion unit generates an appropriate response using natural language generation technology. The generation AI unit can also generate a response by specifying an AI model to be used. The text-to-speech conversion unit converts the text generated by the generation AI unit into speech. For example, the text-to-speech conversion unit converts text to speech using speech synthesis technology. The text-to-speech conversion unit can also convert text to speech by specifying software to be used. The foreign language selection unit selects a foreign language the user wants to learn. For example, it displays a list of selectable languages, allowing the user to select one. The foreign language selection unit can also set selection criteria to allow the user to select the most appropriate language. The conversation field designation unit designates the field and level in which the user wants to converse. For example, it displays field categories, allowing the user to select one. In addition, the conversation field specifying unit can set level definitions so that the user can select the most appropriate level. As a result, the online foreign language conversation class system according to the embodiment can provide an online foreign language conversation class where the user can freely learn a foreign language.

[0030] The speech-to-text conversion unit has an evaluation function that evaluates the user's pronunciation and intonation and provides feedback. For example, the speech-to-text conversion unit incorporates a pronunciation evaluation algorithm into the speech-to-text conversion function to analyze the user's pronunciation and provide feedback. For example, if the pronunciation is incorrect, it points out that part and presents the correct pronunciation. The speech-to-text conversion unit also analyzes the user's voice, evaluates the intonation, and provides feedback. For example, if the intonation is unnatural, it points out that part and presents a more natural intonation. The speech-to-text conversion unit also adds a pronunciation and intonation evaluation function to the speech-to-text conversion function to provide detailed feedback to the user. For example, it specifically indicates areas for improvement in pronunciation and intonation. This enables the user to improve their pronunciation and intonation.

[0031] The speech-to-text conversion unit performs speech conversion between different languages ​​in real time. For example, the speech-to-text conversion unit makes the speech-to-text conversion function multilingual and builds a system that performs speech conversion between different languages ​​in real time. For example, speech conversion from English to French is performed in real time. The speech-to-text conversion unit also develops a multilingual speech-to-text conversion function and converts speech to text according to the language selected by the user. For example, if the user selects Japanese, Japanese speech is converted to text. The speech-to-text conversion unit also develops an algorithm for performing speech conversion between different languages ​​in real time and incorporates it into the speech-to-text conversion function. For example, speech conversion from German to Chinese is performed in real time. This makes real-time speech conversion between different languages ​​possible.

[0032] The speech-to-text conversion unit is applied to presentation and speech practice. For example, the speech-to-text conversion unit applies the speech-to-text conversion function to presentation practice, converting what the user says into text and providing feedback. For example, the content of the presentation is converted into text and points out areas for improvement. The speech-to-text conversion unit also applies the speech-to-text conversion function to speech practice, converting the content of the user's speech into text and analyzing it. For example, the flow and structure of the speech are converted into text and feedback is provided. The speech-to-text conversion unit also uses the speech-to-text conversion function to convert the content of the user's presentation or speech into text in real time, improving the effectiveness of the practice. For example, the pronunciation and intonation are evaluated and feedback is provided. This allows for application to presentation and speech practice.

[0033] The speech-to-text conversion unit is applied to real-time subtitle generation for the hearing impaired. For example, the speech-to-text conversion unit applies the speech-to-text conversion function to real-time subtitle generation for the hearing impaired, converting the content of a conversation or presentation into text and displaying it. For example, remarks made during a meeting are displayed as subtitles in real time. The speech-to-text conversion unit also builds a real-time subtitle generation system for the hearing impaired, and converts speech into text using the speech-to-text conversion function. For example, the content of a lecture or seminar is displayed as subtitles in real time. The speech-to-text conversion unit also uses the speech-to-text conversion function to generate real-time subtitles for the hearing impaired, allowing users to understand the content of a conversation or presentation. For example, the audio of a movie or television program is displayed as subtitles in real time. This allows application to real-time subtitle generation for the hearing impaired.

[0034] The generation AI unit generates personalized responses based on the user's learning history. For example, the generation AI unit improves a chat-type generation AI to generate personalized responses based on the user's learning history. For example, it generates appropriate responses taking into account past learning content. The generation AI unit also develops a chat-type generation AI that analyzes the user's learning history and generates personalized responses based on that data. For example, it generates responses that include supplementary explanations for areas in which the user is weak. The generation AI unit also incorporates a learning history analysis function into the chat-type generation AI to build a system that generates responses based on the user's past learning content. For example, it generates responses that review content that the user previously learned. This makes it possible to generate personalized responses based on the user's learning history.

[0035] The generative AI unit is applied to specific applications such as business simulations and interview practice. For example, the generative AI unit applies chat-type generative AI to business simulations to build a system that allows users to practice business scenarios. For example, it simulates business negotiations and presentations. The generative AI unit also applies chat-type generative AI to interview practice to develop a system that allows users to practice responses to interview questions. For example, it generates appropriate responses to common interview questions. The generative AI unit also applies chat-type generative AI to specific applications to build a system that allows users to practice specific scenarios. For example, it simulates customer support. This allows for specific applications such as business simulations and interview practice.

[0036] The generative AI unit will be used as a teacher support tool in educational settings. For example, the generative AI unit will use chat-type generative AI as a teacher support tool in educational settings to build a system that allows teachers to provide individual instruction to students. For example, it will generate appropriate responses to students' questions. The generative AI unit will also use chat-type generative AI in educational settings to develop tools that allow teachers to supplement lesson content. For example, it will provide additional explanations during class for parts that students find difficult to understand. The generative AI unit will also use chat-type generative AI as a teacher support tool to build a system that monitors students' learning progress in real time and provides appropriate feedback. For example, it will generate responses based on the student's level of understanding. This allows it to be used as a teacher support tool in educational settings.

[0037] The text-to-speech conversion unit can select a voice quality and speaking style according to the user's preferences. For example, the text-to-speech conversion unit adds a function to the text-to-speech conversion function that allows the user to select a voice quality and speaking style according to their preferences. For example, it makes it possible to select a male voice or a female voice, or a calm speaking style or a lively speaking style. The text-to-speech conversion unit also develops a text-to-speech conversion system that allows the user to select a voice quality and speaking style according to their preferences. For example, it generates a voice based on the voice quality and speaking style selected by the user. The text-to-speech conversion unit also adds a customizable voice quality and speaking style selection function to the text-to-speech conversion function, allowing the user to generate a voice according to their preferences. For example, it makes it possible to select a soft voice or a strong voice. This allows the user to select a voice quality and speaking style according to their preferences.

[0038] The text-to-speech conversion unit supports different accents and dialects. For example, the text-to-speech conversion unit adds a function to support different accents and dialects to the text-to-speech conversion function, and generates speech in an accent or dialect selected by the user. For example, American English, British English, Kansai dialect, or Tohoku dialect. The text-to-speech conversion unit also develops a text-to-speech conversion system that supports different accents and dialects, and generates speech based on the accent or dialect selected by the user. For example, Parisian French or Canadian French. The text-to-speech conversion unit also adds a function to select various accents and dialects to the text-to-speech conversion function, allowing the user to generate speech according to their preferences. For example, the user can select standard Japanese or a regional dialect. This makes it possible to support different accents and dialects.

[0039] The text-to-speech conversion unit is applied to the automatic generation of audiobooks and podcasts. For example, the text-to-speech conversion unit applies the text-to-speech conversion function to the automatic generation of audiobooks, building a system that generates audio from text to create audiobooks. For example, novels and essays are audio-recorded. The text-to-speech conversion unit also applies the text-to-speech conversion function to the automatic generation of podcasts, developing a system that generates audio from text to create podcasts. For example, news articles and interviews are audio-recorded. The text-to-speech conversion unit also uses the text-to-speech conversion function to build a system that automatically generates audiobooks and podcasts. For example, educational content and business reports are audio-recorded. This can be applied to the automatic generation of audiobooks and podcasts.

[0040] The text-to-speech conversion unit is applied to audio guides for the visually impaired. For example, the text-to-speech conversion unit applies the text-to-speech conversion function to audio guides for the visually impaired, building a system that generates audio from text to provide information to the visually impaired. For example, it converts exhibit descriptions at museums and art galleries into audio. The text-to-speech conversion unit also develops audio guide systems for the visually impaired, and generates audio guides using the text-to-speech conversion function. For example, it converts information about public facilities and public transportation into audio. The text-to-speech conversion unit also uses the text-to-speech conversion function to build a system that automatically generates audio guides for the visually impaired. For example, it converts the contents of books and websites into audio. This can be applied to audio guides for the visually impaired.

[0041] The foreign language selection unit recommends the most suitable language based on the user's learning history and interests. The foreign language selection unit, for example, analyzes the user's learning history and builds a system that recommends the most suitable language based on that data. For example, recommendations are made based on languages ​​the user has learned in the past and languages ​​in which they are interested. The foreign language selection unit also adds a function that analyzes the user's interests and recommends the most suitable language based on that data. For example, it recommends languages ​​related to cultures or regions in which the user is interested. The foreign language selection unit also develops a system that recommends the most suitable language to the user based on their learning history and interests. For example, it makes recommendations taking into account the level and progress of languages ​​the user has learned in the past. This makes it possible to recommend the most suitable language based on the user's learning history and interests.

[0042] The foreign language selection unit provides information about the culture and history of each language. For example, the foreign language selection unit builds a system that provides information about the culture and history of each language when selecting a foreign language. For example, it explains the background and cultural characteristics of the language. The foreign language selection unit also adds a function to provide information about the culture and history of each language to serve as a reference when the user selects a language. For example, it introduces the origin and development process of the language. The foreign language selection unit also develops a system that provides information about the culture and history when selecting a foreign language. For example, it introduces cultural events and customs of the country or region where the language is spoken. This makes it possible to provide information about the culture and history of each language.

[0043] The foreign language selection unit customizes the system according to the user's learning objectives. For example, the foreign language selection unit builds a system that customizes the system according to the user's learning objectives and recommends the most appropriate foreign language. For example, for a user whose purpose is travel, the foreign language selection unit recommends a language that allows the user to learn phrases that will be useful for travel. The foreign language selection unit also adds a customization function according to the learning objectives and recommends the most appropriate language based on the objective selected by the user. For example, business English is recommended for a user whose purpose is business. The foreign language selection unit also analyzes the user's learning objectives and develops a system that recommends the most appropriate foreign language based on that data. For example, languages ​​related to culture and art are recommended for a user who wants to learn as a hobby. This allows customization according to the user's learning objectives.

[0044] The foreign language selection unit is also applied to learning programming languages ​​and technical terms. For example, the foreign language selection unit applies the foreign language selection function to learning programming languages, building a system that allows users to select the programming language they want to learn. For example, it allows users to select languages ​​such as Python and JavaScript. The foreign language selection unit also applies the foreign language selection function to learning technical terms, developing a system that allows users to select technical terms in the field they want to learn. For example, medical terminology or legal terminology. The foreign language selection unit also adds a foreign language selection function for application to learning programming languages ​​and technical terms, allowing users to select according to their interests and needs. For example, IT terminology or business terminology. This can also be applied to learning programming languages ​​and technical terms.

[0045] The foreign language selection unit links with intercultural exchange events and online exchange platforms. For example, the foreign language selection unit links the foreign language selection function with intercultural exchange events to build a system that allows users to participate in events based on the language selected by the user. For example, a user who selects English can participate in a cultural event in an English-speaking country. The foreign language selection unit also links the foreign language selection function with an online exchange platform to develop a system that allows users to interact with other users in the language selected by the user. For example, a user who selects French can chat with French-speaking users. The foreign language selection unit also adds a foreign language selection function for linking with intercultural exchange events and online exchange platforms, allowing users to interact in the language selected by the user. For example, a user who selects Chinese can make a video call with a Chinese-speaking user. This allows linking with intercultural exchange events and online exchange platforms.

[0046] The conversation field designation unit reflects the user's learning history and progress. For example, the conversation field designation unit analyzes the user's learning history and progress, and builds a system that designates the optimal conversation field and level based on that data. For example, appropriate conversation content is provided taking into account what the user has learned in the past. The conversation field designation unit also adds a function to designate the optimal conversation field and level for a user based on their learning history and progress. For example, conversation content that includes supplementary explanations is provided for areas in which the user is weak. The conversation field designation unit also develops a conversation field and level designation system that reflects the user's learning history and progress. For example, conversation content that reviews what the user has previously learned is provided. This makes it possible to reflect the user's learning history and progress.

[0047] The conversation field designation unit performs customization based on the user's interests and concerns. For example, the conversation field designation unit analyzes the user's interests and concerns and builds a system that designates the optimal conversation field and level based on that data. For example, it provides conversation content based on topics that the user is interested in. The conversation field designation unit also adds a customization function based on interests and concerns and designates the optimal conversation field and level based on topics selected by the user. For example, it provides conversation content based on topics that the user wants to learn as a hobby. The conversation field designation unit also develops a conversation field and level designation system that reflects the user's interests and concerns. For example, it provides conversation content related to fields that the user is interested in. This makes it possible to perform customization based on the user's interests and concerns.

[0048] The conversation field specification unit is applied to preparation for specialized qualification exams and certification exams. For example, the conversation field specification unit applies the conversation field and level specification function to preparation for specialized qualification exams, building a system that allows users to study effectively for exams. For example, it provides preparation conversation content for TOEFL and IELTS. The conversation field specification unit also applies the conversation field and level specification function to preparation for certification exams, developing a system that allows users to study efficiently for exams. For example, it provides preparation conversation content for Business English Proficiency Tests and Licensed Guide Interpreter Exams. The conversation field specification unit also adds a conversation field and level specification function for application to preparation for specialized qualification exams and certification exams, allowing users to study effectively for exams. For example, it provides preparation conversation content for medical English and legal English. This can be applied to preparation for specialized qualification exams and certification exams.

[0049] The conversation field specification unit is applied to learning programs specialized for different industries or occupations. For example, the conversation field specification unit applies the conversation field and level specification function to learning programs specialized for different industries or occupations to build a system in which users can learn conversation content appropriate for their industry or occupation. For example, conversation content specialized for the IT industry or the medical industry is provided. The conversation field specification unit also applies the conversation field and level specification function to learning programs specialized for different industries or occupations to develop a system in which users can learn conversation content appropriate for their industry or occupation. For example, conversation content specialized for the tourism industry or the education industry is provided. The conversation field specification unit also adds a conversation field and level specification function for application to learning programs specialized for industries or occupations, allowing users to learn conversation content appropriate for their industry or occupation. For example, conversation content specialized for the finance industry or the manufacturing industry is provided. This makes it possible to apply the system to learning programs specialized for different industries or occupations.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The online foreign language conversation classroom system can also be equipped with a generation AI unit that generates personalized responses based on the user's learning history. For example, it generates appropriate responses taking into account past learning content. The generation AI unit can also develop a chat-type generation AI that analyzes the user's learning history and generates personalized responses based on that data. For example, it can generate responses that include supplementary explanations for areas in which the user is weak. The generation AI unit can also incorporate a learning history analysis function into the chat-type generation AI to build a system that generates responses based on the user's past learning content. For example, it can generate responses that review content that the user previously learned. This makes it possible to generate personalized responses based on the user's learning history.

[0052] The speech-to-text conversion unit may also be equipped with an evaluation function that evaluates the user's pronunciation and intonation and provides feedback. For example, a pronunciation evaluation algorithm may be incorporated into the speech-to-text conversion function to analyze the user's pronunciation and provide feedback. For example, if the pronunciation is incorrect, the algorithm may point out the incorrect pronunciation and present the correct pronunciation. The speech-to-text conversion unit may also analyze the user's voice, evaluate the intonation, and provide feedback. For example, if the intonation is unnatural, the algorithm may point out the incorrect pronunciation and present the correct intonation. The speech-to-text conversion unit may also add a pronunciation and intonation evaluation function to the speech-to-text conversion function to provide detailed feedback to the user. For example, the algorithm may specifically indicate areas for improvement in pronunciation and intonation. This allows the user to improve their pronunciation and intonation.

[0053] The speech-to-text conversion unit can also perform speech conversion between different languages ​​in real time. For example, the speech-to-text conversion function can be made multilingual, and a system can be built that performs speech conversion between different languages ​​in real time. For example, speech conversion from English to French can be performed in real time. The speech-to-text conversion unit can also develop a multilingual speech-to-text conversion function and convert speech to text according to the language selected by the user. For example, if the user selects Japanese, Japanese speech is converted to text. The speech-to-text conversion unit can also develop an algorithm for performing speech conversion between different languages ​​in real time and incorporate it into the speech-to-text conversion function. For example, speech conversion from German to Chinese can be performed in real time. This makes it possible to perform speech conversion between different languages ​​in real time.

[0054] The speech-to-text conversion unit can also be applied to presentation and speech practice. For example, the speech-to-text conversion function can be applied to presentation practice, converting what a user says into text and providing feedback. For example, the content of the presentation can be converted into text and points out areas for improvement. The speech-to-text conversion unit can also be applied to speech practice, converting the content of a user's speech into text and analyzing it. For example, the flow and structure of the speech can be converted into text and feedback can be provided. The speech-to-text conversion unit can also use the speech-to-text conversion function to convert the content of a user's presentation or speech into text in real time to improve the effectiveness of the practice. For example, the pronunciation and intonation can be evaluated and feedback can be provided. This can be applied to presentation and speech practice.

[0055] The speech-to-text conversion unit can also be applied to real-time subtitle generation for the hearing impaired. For example, the speech-to-text function can be applied to real-time subtitle generation for the hearing impaired, converting the content of a conversation or presentation into text and displaying it. For example, remarks made during a meeting can be displayed as subtitles in real time. The speech-to-text conversion unit can also build a real-time subtitle generation system for the hearing impaired, and convert speech into text using the speech-to-text conversion function. For example, the content of a lecture or seminar can be displayed as subtitles in real time. The speech-to-text conversion unit can also use the speech-to-text conversion function to generate real-time subtitles for the hearing impaired, allowing users to understand the content of a conversation or presentation. For example, the audio of a movie or television program can be displayed as subtitles in real time. This can be applied to real-time subtitle generation for the hearing impaired.

[0056] The generative AI unit can also be applied to specific applications such as business simulations and interview practice. For example, chat-based generative AI can be applied to business simulations to build a system that allows users to practice business scenarios. For example, a simulation of a business negotiation or presentation can be performed. The generative AI unit can also apply chat-based generative AI to interview practice to develop a system that allows users to practice responses to interview questions. For example, it can generate appropriate responses to common interview questions. The generative AI unit can also apply chat-based generative AI to specific applications to build a system that allows users to practice specific scenarios. For example, it can simulate customer support. This allows for specific applications such as business simulations and interview practice.

[0057] The generative AI unit can also be used as a teacher support tool in educational settings. For example, chat-based generative AI can be used as a teacher support tool in educational settings to build a system that allows teachers to provide individual instruction to students. For example, it can generate appropriate responses to student questions. The generative AI unit can also be used in educational settings to develop tools that allow teachers to supplement lesson content. For example, it can provide additional explanations during class to parts that students find difficult to understand. The generative AI unit can also be used as a teacher support tool to build a system that monitors students' learning progress in real time and provides appropriate feedback. For example, it can generate responses based on the student's level of understanding. This allows it to be used as a teacher support tool in educational settings.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The speech-to-text converter converts the user's speech into text. For example, it uses a speech recognition algorithm to convert speech to text. Alternatively, the speech-to-text converter can specify software to use to convert speech to text. Step 2: The generation AI unit generates a response based on the text converted by the speech-to-text conversion unit. For example, it generates an appropriate response using natural language generation technology. The generation AI unit can also specify the AI ​​model to use to generate a response. Step 3: The text-to-speech conversion unit converts the text generated by the generation AI unit into speech. For example, the text-to-speech conversion unit converts the text into speech using speech synthesis technology. The text-to-speech conversion unit can also specify the software to be used to convert the text into speech. Step 4: The foreign language selection unit selects the foreign language the user wants to learn. For example, a list of available languages ​​may be displayed and the user may select one. The foreign language selection unit may also set selection criteria to allow the user to select the most suitable language. Step 5: The conversation field specification unit specifies the field and level in which the user wants to converse. For example, it displays field categories for the user to select. The conversation field specification unit can also set level definitions so that the user can select the most appropriate level.

[0060] (Example 2) The online foreign language conversation classroom system according to an embodiment of the present invention is a system that allows users to freely learn a foreign language by combining a speech-to-text conversion function with a chat-based generation AI. This allows users to efficiently learn a foreign language even in a short amount of time. For example, a user can practice business English conversation in 20 minutes of their free time. Furthermore, users can learn at their own pace without feeling embarrassed because they have no prior knowledge. Furthermore, since the system is available to users around the world, learning can be done from a global perspective.

[0061] The online foreign language conversation classroom system according to the embodiment includes a speech-to-text conversion unit, a generation AI unit, a text-to-speech conversion unit, a foreign language selection unit, and a conversation field designation unit. The speech-to-text conversion unit converts the speech spoken by a user into text. For example, the speech-to-text conversion unit converts speech to text using a speech recognition algorithm. The speech-to-text conversion unit can also convert speech to text by specifying software to be used. The generation AI unit generates a response based on the text converted by the speech-to-text conversion unit. For example, the speech-to-text conversion unit generates an appropriate response using natural language generation technology. The generation AI unit can also generate a response by specifying an AI model to be used. The text-to-speech conversion unit converts the text generated by the generation AI unit into speech. For example, the text-to-speech conversion unit converts text to speech using speech synthesis technology. The text-to-speech conversion unit can also convert text to speech by specifying software to be used. The foreign language selection unit selects a foreign language the user wants to learn. For example, it displays a list of selectable languages, allowing the user to select one. The foreign language selection unit can also set selection criteria to allow the user to select the most appropriate language. The conversation field designation unit designates the field and level in which the user wants to converse. For example, it displays field categories, allowing the user to select one. In addition, the conversation field specifying unit can set level definitions so that the user can select the most appropriate level. As a result, the online foreign language conversation class system according to the embodiment can provide an online foreign language conversation class where the user can freely learn a foreign language.

[0062] The speech-to-text conversion unit has an emotion estimation function that estimates the user's emotion and reflects that emotion in text. For example, when converting a user's speech into text, the speech-to-text conversion unit uses the emotion estimation function to analyze the emotion and reflect it in the text. For example, if the user is angry, the speech-to-text conversion unit generates text that indicates that emotion. The speech-to-text conversion unit also incorporates an emotion estimation algorithm into the speech-to-text conversion function to analyze the user's emotional state in real time and reflect it in the text. For example, if the user is happy, the speech-to-text conversion unit generates text that indicates that emotion. The speech-to-text conversion unit also uses the emotion estimation function to extract emotion from the user's speech and reflect that emotion in the text. For example, if the user is sad, the speech-to-text conversion unit generates text that indicates that emotion. In this way, text that reflects the user's emotion can be generated.

[0063] The speech-to-text conversion unit has an evaluation function that evaluates the user's pronunciation and intonation and provides feedback. For example, the speech-to-text conversion unit incorporates a pronunciation evaluation algorithm into the speech-to-text conversion function to analyze the user's pronunciation and provide feedback. For example, if the pronunciation is incorrect, it points out that part and presents the correct pronunciation. The speech-to-text conversion unit also analyzes the user's voice, evaluates the intonation, and provides feedback. For example, if the intonation is unnatural, it points out that part and presents a more natural intonation. The speech-to-text conversion unit also adds a pronunciation and intonation evaluation function to the speech-to-text conversion function to provide detailed feedback to the user. For example, it specifically indicates areas for improvement in pronunciation and intonation. This enables the user to improve their pronunciation and intonation.

[0064] The speech-to-text conversion unit performs speech conversion between different languages ​​in real time. For example, the speech-to-text conversion unit makes the speech-to-text conversion function multilingual and builds a system that performs speech conversion between different languages ​​in real time. For example, speech conversion from English to French is performed in real time. The speech-to-text conversion unit also develops a multilingual speech-to-text conversion function and converts speech to text according to the language selected by the user. For example, if the user selects Japanese, Japanese speech is converted to text. The speech-to-text conversion unit also develops an algorithm for performing speech conversion between different languages ​​in real time and incorporates it into the speech-to-text conversion function. For example, speech conversion from German to Chinese is performed in real time. This makes real-time speech conversion between different languages ​​possible.

[0065] The speech-to-text conversion unit is applied to presentation and speech practice. For example, the speech-to-text conversion unit applies the speech-to-text conversion function to presentation practice, converting what the user says into text and providing feedback. For example, the content of the presentation is converted into text and points out areas for improvement. The speech-to-text conversion unit also applies the speech-to-text conversion function to speech practice, converting the content of the user's speech into text and analyzing it. For example, the flow and structure of the speech are converted into text and feedback is provided. The speech-to-text conversion unit also uses the speech-to-text conversion function to convert the content of the user's presentation or speech into text in real time, improving the effectiveness of the practice. For example, the pronunciation and intonation are evaluated and feedback is provided. This allows for application to presentation and speech practice.

[0066] The speech-to-text conversion unit is applied to real-time subtitle generation for the hearing impaired. For example, the speech-to-text conversion unit applies the speech-to-text conversion function to real-time subtitle generation for the hearing impaired, converting the content of a conversation or presentation into text and displaying it. For example, remarks made during a meeting are displayed as subtitles in real time. The speech-to-text conversion unit also builds a real-time subtitle generation system for the hearing impaired, and converts speech into text using the speech-to-text conversion function. For example, the content of a lecture or seminar is displayed as subtitles in real time. The speech-to-text conversion unit also uses the speech-to-text conversion function to generate real-time subtitles for the hearing impaired, allowing users to understand the content of a conversation or presentation. For example, the audio of a movie or television program is displayed as subtitles in real time. This allows application to real-time subtitle generation for the hearing impaired.

[0067] The speech-to-text conversion unit converts text according to the user's emotions and provides learning content according to the emotions. The speech-to-text conversion unit, for example, uses an emotion estimation function to convert text according to the user's emotions and customizes the learning content. For example, if the user is feeling stressed, it provides relaxing content. The speech-to-text conversion unit also analyzes the user's emotions in real time and builds a system that converts text according to those emotions. For example, if the user is excited, it generates text that reflects that emotion. The speech-to-text conversion unit also uses the emotion estimation function to develop a system that provides learning content according to the user's emotions. For example, if the user is depressed, it generates text that includes an encouraging message. This makes it possible to provide learning content according to the user's emotions.

[0068] The generation AI unit generates responses according to the user's emotions. For example, the generation AI unit incorporates an emotion estimation function into a chat-type generation AI to build a system that generates responses according to the user's emotions. For example, if the user is sad, it generates an encouraging message. The generation AI unit also uses the emotion estimation function to develop a chat-type generation AI that analyzes the user's emotions and generates responses according to those emotions. For example, if the user is angry, it generates a response that soothes those emotions. The generation AI unit also incorporates an emotion estimation algorithm into the chat-type generation AI to generate personalized responses based on the user's emotions. For example, if the user is happy, it generates a response that shares that emotion. This makes it possible to generate responses according to the user's emotions.

[0069] The generation AI unit generates personalized responses based on the user's learning history. For example, the generation AI unit improves a chat-type generation AI to generate personalized responses based on the user's learning history. For example, it generates appropriate responses taking into account past learning content. The generation AI unit also develops a chat-type generation AI that analyzes the user's learning history and generates personalized responses based on that data. For example, it generates responses that include supplementary explanations for areas in which the user is weak. The generation AI unit also incorporates a learning history analysis function into the chat-type generation AI to build a system that generates responses based on the user's past learning content. For example, it generates responses that review content that the user previously learned. This makes it possible to generate personalized responses based on the user's learning history.

[0070] The generative AI unit is applied to specific applications such as business simulations and interview practice. For example, the generative AI unit applies chat-type generative AI to business simulations to build a system that allows users to practice business scenarios. For example, it simulates business negotiations and presentations. The generative AI unit also applies chat-type generative AI to interview practice to develop a system that allows users to practice responses to interview questions. For example, it generates appropriate responses to common interview questions. The generative AI unit also applies chat-type generative AI to specific applications to build a system that allows users to practice specific scenarios. For example, it simulates customer support. This allows for specific applications such as business simulations and interview practice.

[0071] The generative AI unit will be used as a teacher support tool in educational settings. For example, the generative AI unit will use chat-type generative AI as a teacher support tool in educational settings to build a system that allows teachers to provide individual instruction to students. For example, it will generate appropriate responses to students' questions. The generative AI unit will also use chat-type generative AI in educational settings to develop tools that allow teachers to supplement lesson content. For example, it will provide additional explanations during class for parts that students find difficult to understand. The generative AI unit will also use chat-type generative AI as a teacher support tool to build a system that monitors students' learning progress in real time and provides appropriate feedback. For example, it will generate responses based on the student's level of understanding. This allows it to be used as a teacher support tool in educational settings.

[0072] The generation AI unit generates responses that increase learning motivation based on the user's emotions. For example, the generation AI unit uses an emotion estimation function to build a system that generates responses that increase learning motivation based on the user's emotions. For example, if the user is feeling down, it generates an encouraging message. The generation AI unit also develops a chat-type generation AI that analyzes the user's emotions in real time and generates responses that increase motivation based on those emotions. For example, if the user is tired, it suggests ways to refresh themselves. The generation AI unit also develops a system that uses an emotion estimation function to generate responses that increase learning motivation based on the user's emotions. For example, if the user is feeling unmotivated, it generates an encouraging message. This makes it possible to generate responses that increase learning motivation based on the user's emotions.

[0073] The text-to-speech conversion unit reflects emotions in the generated speech. For example, the text-to-speech conversion unit incorporates an emotion estimation algorithm into the text-to-speech conversion function to build a system that reflects emotions in the generated speech. For example, emotions such as joy and sadness are reflected in the speech. The text-to-speech conversion unit also uses the emotion estimation function to add emotions to speech generated from text. For example, emotionally rich speech is generated based on text entered by a user. The text-to-speech conversion unit also adds an emotion estimation function to the text-to-speech conversion function to develop a system that reflects emotions in the generated speech. For example, emotions such as anger and surprise are reflected in the speech. This makes it possible to reflect emotions in the generated speech.

[0074] The text-to-speech conversion unit can select a voice quality and speaking style according to the user's preferences. For example, the text-to-speech conversion unit adds a function to the text-to-speech conversion function that allows the user to select a voice quality and speaking style according to their preferences. For example, it makes it possible to select a male voice or a female voice, or a calm speaking style or a lively speaking style. The text-to-speech conversion unit also develops a text-to-speech conversion system that allows the user to select a voice quality and speaking style according to their preferences. For example, it generates a voice based on the voice quality and speaking style selected by the user. The text-to-speech conversion unit also adds a customizable voice quality and speaking style selection function to the text-to-speech conversion function, allowing the user to generate a voice according to their preferences. For example, it makes it possible to select a soft voice or a strong voice. This allows the user to select a voice quality and speaking style according to their preferences.

[0075] The text-to-speech conversion unit supports different accents and dialects. For example, the text-to-speech conversion unit adds a function to support different accents and dialects to the text-to-speech conversion function, and generates speech in an accent or dialect selected by the user. For example, American English, British English, Kansai dialect, or Tohoku dialect. The text-to-speech conversion unit also develops a text-to-speech conversion system that supports different accents and dialects, and generates speech based on the accent or dialect selected by the user. For example, Parisian French or Canadian French. The text-to-speech conversion unit also adds a function to select various accents and dialects to the text-to-speech conversion function, allowing the user to generate speech according to their preferences. For example, the user can select standard Japanese or a regional dialect. This makes it possible to support different accents and dialects.

[0076] The text-to-speech conversion unit is applied to the automatic generation of audiobooks and podcasts. For example, the text-to-speech conversion unit applies the text-to-speech conversion function to the automatic generation of audiobooks, building a system that generates audio from text to create audiobooks. For example, novels and essays are audio-recorded. The text-to-speech conversion unit also applies the text-to-speech conversion function to the automatic generation of podcasts, developing a system that generates audio from text to create podcasts. For example, news articles and interviews are audio-recorded. The text-to-speech conversion unit also uses the text-to-speech conversion function to build a system that automatically generates audiobooks and podcasts. For example, educational content and business reports are audio-recorded. This can be applied to the automatic generation of audiobooks and podcasts.

[0077] The text-to-speech conversion unit is applied to audio guides for the visually impaired. For example, the text-to-speech conversion unit applies the text-to-speech conversion function to audio guides for the visually impaired, building a system that generates audio from text to provide information to the visually impaired. For example, it converts exhibit descriptions at museums and art galleries into audio. The text-to-speech conversion unit also develops audio guide systems for the visually impaired, and generates audio guides using the text-to-speech conversion function. For example, it converts information about public facilities and public transportation into audio. The text-to-speech conversion unit also uses the text-to-speech conversion function to build a system that automatically generates audio guides for the visually impaired. For example, it converts the contents of books and websites into audio. This can be applied to audio guides for the visually impaired.

[0078] The text-to-speech conversion unit provides voice feedback according to the user's emotions. For example, the text-to-speech conversion unit uses an emotion estimation function to build a system that provides voice feedback according to the user's emotions. For example, if the user is feeling down, an encouraging message is provided by voice. The text-to-speech conversion unit also develops a text-to-speech conversion system that analyzes the user's emotions in real time and provides voice feedback according to those emotions. For example, if the user is happy, a voice that shares that emotion is provided. The text-to-speech conversion unit also uses an emotion estimation function to develop a system that provides voice feedback based on the user's emotions. For example, if the user is feeling stressed, a relaxing voice is provided. This makes it possible to provide voice feedback according to the user's emotions.

[0079] The foreign language selection unit recommends the most suitable language based on the user's learning history and interests. The foreign language selection unit, for example, analyzes the user's learning history and builds a system that recommends the most suitable language based on that data. For example, recommendations are made based on languages ​​the user has learned in the past and languages ​​in which they are interested. The foreign language selection unit also adds a function that analyzes the user's interests and recommends the most suitable language based on that data. For example, it recommends languages ​​related to cultures or regions in which the user is interested. The foreign language selection unit also develops a system that recommends the most suitable language to the user based on their learning history and interests. For example, it makes recommendations taking into account the level and progress of languages ​​the user has learned in the past. This makes it possible to recommend the most suitable language based on the user's learning history and interests.

[0080] The foreign language selection unit provides information about the culture and history of each language. For example, the foreign language selection unit builds a system that provides information about the culture and history of each language when selecting a foreign language. For example, it explains the background and cultural characteristics of the language. The foreign language selection unit also adds a function to provide information about the culture and history of each language to serve as a reference when the user selects a language. For example, it introduces the origin and development process of the language. The foreign language selection unit also develops a system that provides information about the culture and history when selecting a foreign language. For example, it introduces cultural events and customs of the country or region where the language is spoken. This makes it possible to provide information about the culture and history of each language.

[0081] The foreign language selection unit customizes the system according to the user's learning objectives. For example, the foreign language selection unit builds a system that customizes the system according to the user's learning objectives and recommends the most appropriate foreign language. For example, for a user whose purpose is travel, the foreign language selection unit recommends a language that allows the user to learn phrases that will be useful for travel. The foreign language selection unit also adds a customization function according to the learning objectives and recommends the most appropriate language based on the objective selected by the user. For example, business English is recommended for a user whose purpose is business. The foreign language selection unit also analyzes the user's learning objectives and develops a system that recommends the most appropriate foreign language based on that data. For example, languages ​​related to culture and art are recommended for a user who wants to learn as a hobby. This allows customization according to the user's learning objectives.

[0082] The foreign language selection unit is also applied to learning programming languages ​​and technical terms. For example, the foreign language selection unit applies the foreign language selection function to learning programming languages, building a system that allows users to select the programming language they want to learn. For example, it allows users to select languages ​​such as Python and JavaScript. The foreign language selection unit also applies the foreign language selection function to learning technical terms, developing a system that allows users to select technical terms in the field they want to learn. For example, medical terminology or legal terminology. The foreign language selection unit also adds a foreign language selection function for application to learning programming languages ​​and technical terms, allowing users to select according to their interests and needs. For example, IT terminology or business terminology. This can also be applied to learning programming languages ​​and technical terms.

[0083] The foreign language selection unit links with intercultural exchange events and online exchange platforms. For example, the foreign language selection unit links the foreign language selection function with intercultural exchange events to build a system that allows users to participate in events based on the language selected by the user. For example, a user who selects English can participate in a cultural event in an English-speaking country. The foreign language selection unit also links the foreign language selection function with an online exchange platform to develop a system that allows users to interact with other users in the language selected by the user. For example, a user who selects French can chat with French-speaking users. The foreign language selection unit also adds a foreign language selection function for linking with intercultural exchange events and online exchange platforms, allowing users to interact in the language selected by the user. For example, a user who selects Chinese can make a video call with a Chinese-speaking user. This allows linking with intercultural exchange events and online exchange platforms.

[0084] The foreign language selection unit recommends the optimal language to learn based on the user's emotions. The foreign language selection unit, for example, uses an emotion estimation function to build a system that recommends the optimal language to learn based on the user's emotions. For example, if the user is relaxed, it recommends language learning that will help them relax. The foreign language selection unit also adds a function that analyzes the user's emotions in real time and recommends the optimal language to learn based on those emotions. For example, if the user is excited, it recommends language learning that will make use of that emotion. The foreign language selection unit also uses the emotion estimation function to develop a system that recommends the optimal language to learn based on the user's emotions. For example, if the user is depressed, it recommends language learning that includes an encouraging message. This makes it possible to recommend the optimal language to learn based on the user's emotions.

[0085] The conversation field designation unit provides optimal learning content according to the user's emotions. The conversation field designation unit, for example, uses an emotion estimation function to build a system that provides optimal learning content according to the user's emotions. For example, if the user is feeling stressed, it provides conversation content that helps the user relax. The conversation field designation unit also adds a function that analyzes the user's emotions in real time and specifies the optimal conversation field and level according to those emotions. For example, if the user is excited, it provides conversation content that makes use of that emotion. The conversation field designation unit also uses the emotion estimation function to develop a system that provides optimal learning content based on the user's emotions. For example, if the user is depressed, it provides conversation content that includes an encouraging message. This makes it possible to provide optimal learning content according to the user's emotions.

[0086] The conversation field designation unit reflects the user's learning history and progress. For example, the conversation field designation unit analyzes the user's learning history and progress, and builds a system that designates the optimal conversation field and level based on that data. For example, appropriate conversation content is provided taking into account what the user has learned in the past. The conversation field designation unit also adds a function to designate the optimal conversation field and level for a user based on their learning history and progress. For example, conversation content that includes supplementary explanations is provided for areas in which the user is weak. The conversation field designation unit also develops a conversation field and level designation system that reflects the user's learning history and progress. For example, conversation content that reviews what the user has previously learned is provided. This makes it possible to reflect the user's learning history and progress.

[0087] The conversation field designation unit performs customization based on the user's interests and concerns. For example, the conversation field designation unit analyzes the user's interests and concerns and builds a system that designates the optimal conversation field and level based on that data. For example, it provides conversation content based on topics that the user is interested in. The conversation field designation unit also adds a customization function based on interests and concerns and designates the optimal conversation field and level based on topics selected by the user. For example, it provides conversation content based on topics that the user wants to learn as a hobby. The conversation field designation unit also develops a conversation field and level designation system that reflects the user's interests and concerns. For example, it provides conversation content related to fields that the user is interested in. This makes it possible to perform customization based on the user's interests and concerns.

[0088] The conversation field specification unit is applied to preparation for specialized qualification exams and certification exams. For example, the conversation field specification unit applies the conversation field and level specification function to preparation for specialized qualification exams, building a system that allows users to study effectively for exams. For example, it provides preparation conversation content for TOEFL and IELTS. The conversation field specification unit also applies the conversation field and level specification function to preparation for certification exams, developing a system that allows users to study efficiently for exams. For example, it provides preparation conversation content for Business English Proficiency Tests and Licensed Guide Interpreter Exams. The conversation field specification unit also adds a conversation field and level specification function for application to preparation for specialized qualification exams and certification exams, allowing users to study effectively for exams. For example, it provides preparation conversation content for medical English and legal English. This can be applied to preparation for specialized qualification exams and certification exams.

[0089] The conversation field specification unit is applied to learning programs specialized for different industries or occupations. For example, the conversation field specification unit applies the conversation field and level specification function to learning programs specialized for different industries or occupations to build a system in which users can learn conversation content appropriate for their industry or occupation. For example, conversation content specialized for the IT industry or the medical industry is provided. The conversation field specification unit also applies the conversation field and level specification function to learning programs specialized for different industries or occupations to develop a system in which users can learn conversation content appropriate for their industry or occupation. For example, conversation content specialized for the tourism industry or the education industry is provided. The conversation field specification unit also adds a conversation field and level specification function for application to learning programs specialized for industries or occupations, allowing users to learn conversation content appropriate for their industry or occupation. For example, conversation content specialized for the finance industry or the manufacturing industry is provided. This makes it possible to apply the system to learning programs specialized for different industries or occupations.

[0090] The conversation field designation unit recommends the optimal learning field and level based on the user's emotions. The conversation field designation unit, for example, uses an emotion estimation function to build a system that recommends the optimal learning field and level based on the user's emotions. For example, if the user is relaxed, it provides conversation content that will help the user relax. The conversation field designation unit also adds a function that analyzes the user's emotions in real time and recommends the optimal learning field and level based on those emotions. For example, if the user is excited, it provides conversation content that will make use of that emotion. The conversation field designation unit also uses the emotion estimation function to develop a system that recommends the optimal learning field and level based on the user's emotions. For example, if the user is depressed, it provides conversation content that includes an encouraging message. This makes it possible to recommend the optimal learning field and level based on the user's emotions.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] The online foreign language conversation classroom system can also be equipped with a generation AI unit that generates personalized responses based on the user's learning history. For example, it generates appropriate responses taking into account past learning content. The generation AI unit can also develop a chat-type generation AI that analyzes the user's learning history and generates personalized responses based on that data. For example, it can generate responses that include supplementary explanations for areas in which the user is weak. The generation AI unit can also incorporate a learning history analysis function into the chat-type generation AI to build a system that generates responses based on the user's past learning content. For example, it can generate responses that review content that the user previously learned. This makes it possible to generate personalized responses based on the user's learning history.

[0093] The speech-to-text conversion unit may also have an emotion estimation function that estimates a user's emotion and reflects that emotion in text. For example, when converting a user's speech into text, the emotion estimation function is used to analyze the emotion and reflect it in the text. For example, if the user is angry, text indicating that emotion is generated. The speech-to-text conversion unit may also incorporate an emotion estimation algorithm into the speech-to-text conversion function to analyze the user's emotional state in real time and reflect that emotion in the text. For example, if the user is happy, text indicating that emotion is generated. The speech-to-text conversion unit may also use the emotion estimation function to extract emotion from the user's speech and reflect that emotion in the text. For example, if the user is sad, text indicating that emotion is generated. This makes it possible to generate text that reflects the user's emotion.

[0094] The speech-to-text conversion unit may also be equipped with an evaluation function that evaluates the user's pronunciation and intonation and provides feedback. For example, a pronunciation evaluation algorithm may be incorporated into the speech-to-text conversion function to analyze the user's pronunciation and provide feedback. For example, if the pronunciation is incorrect, the algorithm may point out the incorrect pronunciation and present the correct pronunciation. The speech-to-text conversion unit may also analyze the user's voice, evaluate the intonation, and provide feedback. For example, if the intonation is unnatural, the algorithm may point out the incorrect pronunciation and present the correct intonation. The speech-to-text conversion unit may also add a pronunciation and intonation evaluation function to the speech-to-text conversion function to provide detailed feedback to the user. For example, the algorithm may specifically indicate areas for improvement in pronunciation and intonation. This allows the user to improve their pronunciation and intonation.

[0095] The speech-to-text conversion unit can also perform speech conversion between different languages ​​in real time. For example, the speech-to-text conversion function can be made multilingual, and a system can be built that performs speech conversion between different languages ​​in real time. For example, speech conversion from English to French can be performed in real time. The speech-to-text conversion unit can also develop a multilingual speech-to-text conversion function and convert speech to text according to the language selected by the user. For example, if the user selects Japanese, Japanese speech is converted to text. The speech-to-text conversion unit can also develop an algorithm for performing speech conversion between different languages ​​in real time and incorporate it into the speech-to-text conversion function. For example, speech conversion from German to Chinese can be performed in real time. This makes it possible to perform speech conversion between different languages ​​in real time.

[0096] The speech-to-text conversion unit can also be applied to presentation and speech practice. For example, the speech-to-text conversion function can be applied to presentation practice, converting what a user says into text and providing feedback. For example, the content of the presentation can be converted into text and points out areas for improvement. The speech-to-text conversion unit can also be applied to speech practice, converting the content of a user's speech into text and analyzing it. For example, the flow and structure of the speech can be converted into text and feedback can be provided. The speech-to-text conversion unit can also use the speech-to-text conversion function to convert the content of a user's presentation or speech into text in real time to improve the effectiveness of the practice. For example, the pronunciation and intonation can be evaluated and feedback can be provided. This can be applied to presentation and speech practice.

[0097] The speech-to-text conversion unit can also be applied to real-time subtitle generation for the hearing impaired. For example, the speech-to-text function can be applied to real-time subtitle generation for the hearing impaired, converting the content of a conversation or presentation into text and displaying it. For example, remarks made during a meeting can be displayed as subtitles in real time. The speech-to-text conversion unit can also build a real-time subtitle generation system for the hearing impaired, and convert speech into text using the speech-to-text conversion function. For example, the content of a lecture or seminar can be displayed as subtitles in real time. The speech-to-text conversion unit can also use the speech-to-text conversion function to generate real-time subtitles for the hearing impaired, allowing users to understand the content of a conversation or presentation. For example, the audio of a movie or television program can be displayed as subtitles in real time. This can be applied to real-time subtitle generation for the hearing impaired.

[0098] The speech-to-text conversion unit can also perform text conversion according to the user's emotions and provide learning content according to the emotions. For example, using the emotion estimation function, text conversion according to the user's emotions can be performed to customize learning content. For example, if the user is feeling stressed, learning content that helps them relax can be provided. The speech-to-text conversion unit can also build a system that analyzes the user's emotions in real time and performs text conversion according to those emotions. For example, if the user is excited, text that reflects that emotion can be generated. The speech-to-text conversion unit can also use the emotion estimation function to develop a system that provides learning content according to the user's emotions. For example, if the user is depressed, text containing an encouraging message can be generated. This makes it possible to provide learning content according to the user's emotions.

[0099] The generation AI unit can also generate responses based on the user's emotions. For example, an emotion estimation function can be incorporated into a chat-type generation AI to build a system that generates responses based on the user's emotions. For example, if the user is sad, an encouraging message can be generated. The generation AI unit can also use the emotion estimation function to develop a chat-type generation AI that analyzes the user's emotions and generates a response based on those emotions. For example, if the user is angry, a response that soothes the emotion can be generated. The generation AI unit can also incorporate an emotion estimation algorithm into the chat-type generation AI to generate personalized responses based on the user's emotions. For example, if the user is happy, a response that shares that emotion can be generated. This makes it possible to generate responses based on the user's emotions.

[0100] The generative AI unit can also be applied to specific applications such as business simulations and interview practice. For example, chat-based generative AI can be applied to business simulations to build a system that allows users to practice business scenarios. For example, a simulation of a business negotiation or presentation can be performed. The generative AI unit can also apply chat-based generative AI to interview practice to develop a system that allows users to practice responses to interview questions. For example, it can generate appropriate responses to common interview questions. The generative AI unit can also apply chat-based generative AI to specific applications to build a system that allows users to practice specific scenarios. For example, it can simulate customer support. This allows for specific applications such as business simulations and interview practice.

[0101] The generative AI unit can also be used as a teacher support tool in educational settings. For example, chat-based generative AI can be used as a teacher support tool in educational settings to build a system that allows teachers to provide individual instruction to students. For example, it can generate appropriate responses to student questions. The generative AI unit can also be used in educational settings to develop tools that allow teachers to supplement lesson content. For example, it can provide additional explanations during class to parts that students find difficult to understand. The generative AI unit can also be used as a teacher support tool to build a system that monitors students' learning progress in real time and provides appropriate feedback. For example, it can generate responses based on the student's level of understanding. This allows it to be used as a teacher support tool in educational settings.

[0102] The processing flow of the second embodiment will be briefly explained below.

[0103] Step 1: The speech-to-text converter converts the user's speech into text. For example, it uses a speech recognition algorithm to convert speech to text. Alternatively, the speech-to-text converter can specify software to use to convert speech to text. Step 2: The generation AI unit generates a response based on the text converted by the speech-to-text conversion unit. For example, it generates an appropriate response using natural language generation technology. The generation AI unit can also specify the AI ​​model to use to generate a response. Step 3: The text-to-speech conversion unit converts the text generated by the generation AI unit into speech. For example, the text-to-speech conversion unit converts the text into speech using speech synthesis technology. The text-to-speech conversion unit can also specify the software to be used to convert the text into speech. Step 4: The foreign language selection unit selects the foreign language the user wants to learn. For example, a list of available languages ​​may be displayed and the user may select one. The foreign language selection unit may also set selection criteria to allow the user to select the most suitable language. Step 5: The conversation field specification unit specifies the field and level in which the user wants to converse. For example, it displays field categories for the user to select. The conversation field specification unit can also set level definitions so that the user can select the most appropriate level.

[0104] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0105] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0106] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0109] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0110] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0111] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0112] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0113] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0114] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0115] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0116] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0117] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0118] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0119] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0120] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0121] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0124] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0125] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0126] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0129] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0132] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0134] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0136] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0137] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0138] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0144] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0145] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0146] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0147] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0148] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0149] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0150] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0151] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0152] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0153] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0154] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0155] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0156] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0157] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0158] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0159] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0160] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0161] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0162] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0163] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0164] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0165] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0166] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0167] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0168] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0169] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0170] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0171] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a speech-to-text converter that converts speech into text; a generation AI unit that generates a response based on the text converted by the speech-to-text conversion unit; a text-to-speech conversion unit that converts the text generated by the generation AI unit into speech; A foreign language selection section for selecting the foreign language you want to learn; A conversation field designation unit that designates the field and level of conversation desired is provided. A system characterized by:

2. The speech-to-text conversion unit Emotion estimation function that estimates the user's emotions and reflects those emotions in the text 2. The system of claim 1.

3. The speech-to-text conversion unit Includes an evaluation function that evaluates the user's pronunciation and intonation and provides feedback 2. The system of claim 1.

4. The speech-to-text conversion unit Real-time speech conversion between different languages 2. The system of claim 1.

5. The speech-to-text conversion unit Applied to practice presentations and speeches 2. The system of claim 1.

Images